Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Estimating log models: to transform or not to transform?

W G Manning1, J Mullahy

  • 1Department of Health Studies, Harris School of Public Policy Studies, The University of Chicago, IL 60637, USA. w-manning@uchicago.edu

Journal of Health Economics
|July 27, 2001
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Interpreting results in mental health research.

Mental health services research·2002
Same author

Live long, live well: quantifying the health of heterogeneous populations.

Health economics·2001
Same author

Health insurance: tradeoffs revisited.

Journal of health economics·2001
Same author

Cost-effectiveness of systematic depression treatment for high utilizers of general medical care.

Archives of general psychiatry·2001
Same author

Effect of multiple-source entry on price competition after patent expiration in the pharmaceutical industry.

Health services research·2000
Same author

Randomized trial of a depression management program in high utilizers of medical care.

Archives of family medicine·2000
Same journal

Competition matters: Uniform vs. indication-based pricing of pharmaceuticals.

Journal of health economics·2026
Same journal

Integrating equity and productivity in health evaluation.

Journal of health economics·2026
Same journal

Income and immunity: The consequences of social security administration reform for childhood infection risk.

Journal of health economics·2026
Same journal

When fewer children mean shorter lives: Fertility policy and elderly well-being in China.

Journal of health economics·2026
Same journal

Health dynamics and reporting bias at retirement: An analysis using high-frequency data.

Journal of health economics·2026
Same journal

Intertemporal coordination in volunteer markets.

Journal of health economics·2026
See all related articles

Choosing the right statistical model for skewed health economics data is crucial. This study evaluates various log model estimators, finding no single best approach and offering an algorithm to guide selection for optimal precision.

Area of Science:

  • Health Economics
  • Econometrics
  • Biostatistics

Background:

  • Health economists frequently encounter skewed outcome variables like healthcare utilization and expenditures.
  • Log models are commonly employed to address data skewness in health economics research.
  • Existing literature offers several estimation methods for log models, including ordinary least-squares (OLS) on the natural logarithm of the outcome (ln(y)) and generalized linear models (GLMs).

Purpose of the Study:

  • To assess the econometric performance of alternative log model estimators.
  • To evaluate estimators based on bias and precision when dealing with skewed data, heteroscedasticity, and heavy tails.
  • To provide guidance on selecting the most appropriate estimator for skewed health economics data.

Main Methods:

Related Experiment Videos

  • Econometric analysis of alternative estimators for log models.
  • Simulation or empirical examination of estimator performance under various data conditions (skewness, heteroscedasticity, heavy tails).
  • Development of an algorithm for estimator selection.

    • Main Results:

    • No single alternative estimator consistently outperformed others across all examined data conditions.
    • The choice of estimator significantly impacts precision, even when estimators are statistically consistent.
    • The study proposes a practical algorithm to aid researchers in selecting the most suitable estimator.

    Conclusions:

    • The performance of log model estimators varies substantially depending on data characteristics.
    • Careful selection of an appropriate estimator is essential to avoid significant precision losses in health economics research.
    • The developed algorithm offers a systematic approach to choosing among alternative estimators for skewed health outcomes.